© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48813
    Prev
    Next
    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harbour
    0.43
    肩
    0.39
    हाई
    0.38
    circle
    0.38
     seemingly
    0.37
     circle
    0.37
    രം
    0.37
     noticeably
    0.37
     कृत
    0.37
    ipy
    0.36
    POSITIVE LOGITS
    hões
    0.46
     orders
    0.43
     pretend
    0.40
     fiche
    0.40
     ORDERS
    0.39
     só
    0.39
    쏴
    0.38
     Orders
    0.38
    ద్దా
    0.38
    سة
    0.37
    Activations Density 0.003%

    No Known Activations